Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

about word_embedding_c of WordKVMN #8

Open
Alexia1994 opened this issue Apr 30, 2021 · 1 comment
Open

about word_embedding_c of WordKVMN #8

Alexia1994 opened this issue Apr 30, 2021 · 1 comment

Comments

@Alexia1994
Copy link

Excuse me, why self.word_embedding_c = nn.Embedding(10, hidden_size)? I do not really understand why is 10.
Thanks for your answering : )

@yuanheTian
Copy link
Collaborator

Excuse me, why self.word_embedding_c = nn.Embedding(10, hidden_size)? I do not really understand why is 10.
Thanks for your answering : )

Thanks for asking!

That number actually should be the size of the value set. We map the value to its corresponding index in line 353 of wmseg_model.py. The range of the value index should be [0, 4]. So, using 10 here will be enough to map the index to its embedding.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants